Robotics

Language to Rewards for Robotic Skill Synthesis

First page

Paper summary

Google's Language-to-Rewards uses LLMs to define reward parameters for robotic RL.

Ask this paper

Key points

LLM-defined rewards: Uses LLMs to translate natural-language task descriptions into optimizable reward parameters for downstream RL training.

Real-robot evaluation: Evaluated on a real robot arm, not just in simulation, validating that the approach survives sim-to-real challenges.

Emergent skills: Complex manipulation skills including non-prehensile pushing emerge from the LLM-specified rewards alone.

Natural robot programming: Positions natural language as a practical interface for programming robot behaviors without handcrafting reward functions.

Every Monday